Loaders#

Overview#

Loaders are used to load data from sources and parse it into Artifacts s. Each loader can be used to load a single “source” with load() or multiple sources with load_collection() .

File#

The following Loaders load a file using a AmazonS3FileManagerDriver and loads the resulting data into an Artifacts for the respective file type.

As a convenience, File Loaders also have a save() method that can save an Artifact to a destination.

from griptape.drivers.file_manager.local import LocalFileManagerDriver
from griptape.loaders import TextLoader

loader = TextLoader(file_manager_driver=LocalFileManagerDriver())

data = loader.load("tests/resources/test.txt")

data.value = data.value.replace("foo", "bar")

loader.save("tests/resources/test.txt", data)

Text#

Loads text files into TextArtifact s:

import urllib.request
from pathlib import Path

from griptape.loaders import TextLoader

TextLoader().load("tests/resources/test.txt")

urllib.request.urlretrieve("https://example-files.online-convert.com/document/txt/example.txt", "example.txt")

TextLoader().load(Path("example.txt"))

TextLoader().load_collection(["tests/resources/test.txt", Path("example.txt")])

PDF#

Loads PDF files into ListArtifact s, where each element is a TextArtifact containing a page of the PDF:

import urllib.request
from pathlib import Path

from griptape.loaders import PdfLoader

urllib.request.urlretrieve("https://arxiv.org/pdf/1706.03762.pdf", "attention.pdf")

#  Load a single PDF file

PdfLoader().load("attention.pdf")

#  You can also pass a Path object

PdfLoader().load(Path("attention.pdf"))

urllib.request.urlretrieve("https://arxiv.org/pdf/1706.03762.pdf", "CoT.pdf")

#  Load multiple PDF files

PdfLoader().load_collection([Path("attention.pdf"), Path("CoT.pdf")])

CSV#

Loads CSV files into ListArtifact s, where each element is a TextArtifact containing a row of the CSV:

from pathlib import Path

from griptape.loaders import CsvLoader

#  Load a single CSV file

CsvLoader().load("tests/resources/cities.csv")

#  You can also pass a Path object

CsvLoader().load(Path("tests/resources/cities.csv"))

#  Load multiple CSV files

CsvLoader().load_collection([Path("tests/resources/cities.csv"), "tests/resources/addresses.csv"])

Image#

Loads images into ImageArtifact s:

from pathlib import Path

from griptape.loaders import ImageLoader

#  Load an image from disk

ImageLoader().load("tests/resources/mountain.png")

#  You can also pass a Path object

ImageLoader().load(Path("tests/resources/mountain.png"))

By default, the Image Loader will load images in their native format, but not all models work on all formats. To normalize the format of Artifacts returned by the Loader, set the format field.

from pathlib import Path

from griptape.loaders import ImageLoader

#  Load a single image in BMP format

ImageLoader(format="bmp").load("tests/resources/mountain.png")

#  You can also pass a Path object

ImageLoader(format="bmp").load(Path("tests/resources/mountain.png"))

#  Load multiple images in BMP format

ImageLoader().load_collection([Path("tests/resources/mountain.png"), "tests/resources/cow.png"])

Audio#

Loads audio files into AudioArtifact s:

The Loader will load audio in its native format and populates the resulting Artifact’s format field by making a best-effort guess of the underlying audio format using the filetype package.

from pathlib import Path

from griptape.loaders import AudioLoader

#  Load an image from disk

AudioLoader().load("tests/resources/sentences.wav")

#  You can also pass a Path object

AudioLoader().load(Path("tests/resources/sentences.wav"))

JSON#

Loads JSON files into JsonArtifact s:

from pathlib import Path

from griptape.loaders import JsonLoader

#  Load an image from disk

JsonLoader().load("tests/resources/test.json")

#  You can also pass a Path object

JsonLoader().load(Path("tests/resources/test.json"))

Web#

Scrapes web pages using a BaseWebScraperDriver and loads the resulting text into TextArtifact s.

from griptape.loaders import WebLoader

WebLoader().load("https://www.griptape.ai")

WebLoader().load_collection(["https://www.griptape.ai", "https://docs.griptape.ai"])

SQL#

Loads data from a SQL database using a AmazonRedshiftSqlDriver and loads the resulting data into ListArtifact s, where each element is a TextArtifact containing a row of the SQL query.

from griptape.drivers.sql.sql_driver import SqlDriver
from griptape.loaders import SqlLoader

SqlLoader(sql_driver=SqlDriver(engine_url="sqlite:///:memory:")).load("SELECT foo, bar")

SqlLoader(sql_driver=SqlDriver(engine_url="sqlite:///:memory:")).load_collection(
    ["SELECT foo, bar;", "SELECT fizz, buzz;"]
)

Email#

Loads data from an imap email server into a ListArtifact s, where each element is a TextArtifact containing an email.

from griptape.loaders import EmailLoader

loader = EmailLoader(imap_url="an.email.server.hostname", username="username", password="password")

loader.load(EmailLoader.EmailQuery(label="INBOX"))

loader.load_collection([EmailLoader.EmailQuery(label="INBOX"), EmailLoader.EmailQuery(label="SENT")])

Loaders

Contents